How much time will I actually save with Fazm?

Most users report saving 45-90 minutes per day on repetitive tasks. The biggest time savings come from email management (drafting replies, sorting, archiving), form filling (expense reports, CRM updates, applications), research (comparing products, gathering data from multiple sites), and social media (cross-posting, scheduling, replying). For example, booking a flight that normally takes 10 minutes of clicking through airline sites takes a single voice command with Fazm. Filing an expense report that requires opening a PDF, extracting numbers, and entering them into a spreadsheet becomes one spoken sentence. The more repetitive and multi-step your daily work is, the more time you get back.

What exactly can Fazm control?

Fazm controls everything you can do manually on your Mac. That includes mouse movements and clicks, keyboard typing, browser navigation and form filling, app switching, file management in Finder, and system-level actions. It uses direct browser DOM control for web interactions - meaning it reads and manipulates the actual page structure rather than taking screenshots and guessing where to click. For native macOS apps, Fazm uses accessibility APIs to interact with buttons, menus, text fields, and other UI elements. This works across any application: Chrome, Safari, VS Code, Slack, Figma, Terminal, Mail, Calendar, and more.

How is Fazm different from ChatGPT or Claude?

Chatbots like ChatGPT and Claude give you answers in a conversation window. Fazm takes action directly on your computer. When you say 'reply to Sarah's email,' Fazm opens your email app, finds Sarah's message, writes a contextual reply, and sends it. A chatbot would tell you what to write, but you still have to do all the clicking and typing yourself. Fazm moves your mouse, types on your keyboard, clicks buttons, and navigates between apps. It is a computer agent, not a chat assistant.

How does the memory layer work?

Fazm builds a personal knowledge graph by extracting information from your files, browsing history, conversations, and daily activity. Over time, it learns your contacts (names, emails, relationships), accounts and credentials, preferences (formatting, tone, scheduling habits), and frequently used workflows. In your first week, you might say 'Reply to Sarah's email, she's my cofounder, her email is sarah@acme.com.' By week four, you just say 'Reply to Sarah' because Fazm already knows who she is. By week eight, Fazm can draft the reply before you even ask. All of this data stays locally on your Mac - your knowledge graph never leaves your machine or gets sent to any cloud service.

Is Fazm safe? Can it mess up my computer?

Safety is built into every layer of Fazm. You watch every action in real-time on your screen - Fazm moves your mouse and types visibly, so there is nothing hidden. You can stop any action at any point by pressing a keyboard shortcut. Fazm also shows you what it plans to do before executing destructive actions like deleting files or sending emails, giving you a chance to confirm or cancel. Because Fazm is open source, the code is fully auditable on GitHub. There is no hidden behavior, no background processes making changes you cannot see, and no actions that bypass your screen.

What platforms does Fazm support?

Fazm currently supports macOS, running natively on both Apple Silicon (M1, M2, M3, M4) and Intel Macs. It is built with Swift and uses macOS-specific frameworks like ScreenCaptureKit for screen analysis and Accessibility APIs for app control, which is why macOS is the primary platform. Windows and Linux support are on the roadmap but do not have release dates yet. You can also control your Mac remotely from your phone using Fazm Remote, which gives you voice access to your desktop while you are away from your computer.

How does Fazm voice input work?

One keyboard shortcut activates push-to-talk. Hold the key, speak naturally about what you need done, and release. Fazm transcribes your speech locally using on-device models, so there is no network latency for the voice recognition step. You do not need wake words like 'Hey Siri' or 'OK Google' - just press and talk. You can also type commands into the floating toolbar if you prefer text input. Fazm understands natural language, so you do not need to memorize specific commands. Say 'book me a flight to Tokyo next Thursday' or 'find the cheapest AirPods on Amazon' and Fazm figures out the steps.

Is my data sent to the cloud?

Fazm processes screen analysis and memory entirely on your machine. The personal knowledge graph, file indexing, and screen capture all run locally. The only data that leaves your Mac is the intent - a text description of what you want to accomplish, which is sent to the AI model (Claude or GPT) for action planning. Your actual screen content, file contents, browsing history, and personal knowledge graph never leave your computer. Fazm is also open source, so you can verify exactly what data is transmitted by reading the code on GitHub. For users who need complete air-gapped operation, local model support is planned.

Back to Blog

AI Agent Permissions - Why Local Agents Do Not Have the Cloud Permission Problem

Fazm Team·March 13, 2026·3 min read

permissionssecuritylocal-firstcloud-agentscomparison

AI Agent Permissions - Local vs Cloud

One of the most common complaints about cloud-based AI agents is the permission model. You grant folder access for a task, the task completes, and the access lingers. How do you revoke it? When does it expire? What exactly can the agent still see?

This is a fundamental problem with the cloud agent architecture, and it goes away entirely with a local agent.

The Cloud Permission Problem

Cloud agents like Cowork work by running in a remote environment that needs access to your local files. This means:

You grant access to a project folder
The agent copies or syncs those files to a remote VM
The task completes
The files are... still there? Maybe? Who knows?

There is no clear lifecycle for these permissions. The agent might retain cached copies. The remote environment might persist between sessions. The permission grant might apply to more files than you intended.

Why Local Agents Avoid This

A local agent does not need permission grants because it is already running on your machine. It sees what is on your screen - the same things you can see. When the task is done, there is nothing to revoke because the agent never copied your data anywhere.

The interaction model is fundamentally different:

Cloud agent: "Here are my files. Process them remotely. Now give them back."
Local agent: "Look at my screen. Do what I asked. Done."

No file copying. No remote storage. No lingering permissions. The agent sees what is on screen, acts on it, and that is the end of it.

The Screen-Level Boundary

With a local agent using accessibility APIs, the permission boundary is your screen. The agent can interact with whatever apps are open and visible. Close an app and the agent can no longer interact with it. It is a natural, intuitive permission model that matches how you already think about what is "active" on your computer.

This does not mean local agents have no security considerations. An agent controlling your mouse and keyboard can still do damage if it clicks the wrong thing. That is why bounded tools and approval flows matter. But the permission question - what can the agent access and for how long - is dramatically simpler.

Fazm runs locally on your Mac with no remote file access. Open source on GitHub. Discussed in r/ClaudeAI.

AI Agent Permissions - Why Local Agents Do Not Have the Cloud Permission Problem

AI Agent Permissions - Local vs Cloud

The Cloud Permission Problem

Why Local Agents Avoid This

The Screen-Level Boundary

Related Posts

Why Local AI Agents Can Access Your NAS (And Cloud Agents Cannot)

Why Local-First AI Agents Are the Future (And Why It Matters for Your Privacy)

AI Agent vs Chatbot vs Copilot: What Is the Difference?